The paper argues that evaluating privacy‑enhancing technologies (PETs) solely through image classification is insufficient because classification remains robust to many geometric and local perturbations. It proposes a compute‑aware multi‑task protocol that uses lightweight proxy tasks to assess PETs across various transformations, revealing that PETs with similar classification accuracy can perform very differently on other vision tasks. The study demonstrates the necessity of broader evaluation metrics beyond classification to truly gauge PET effectiveness.
By Leon Ranke, Wolfgang H\"ubner, Ronny Hug, Michael Arens, J\"urgen Beyerer
Aegis is a client‑side defense for medical federated learning that protects against model inversion attacks by adding a masking gradient derived from locally synthesized data. The method exploits the fact that attacks fail when the effective batch size exceeds the model’s leakage capacity, turning this bottleneck into a privacy guarantee. Experiments on MNIST, CIFAR‑10, and MedMNIST datasets show that Aegis neutralizes state‑of‑the‑art attacks while preserving model accuracy and adding only modest overhead.
By Chaoyu Zhang, Shanghao Shi, Heng Jin, Ning Wang, Y. Thomas Hou, Wenjing Lou
arXiv:2606. 25375v2 Announce Type: replace-cross Abstract: With the rapid adoption of generative AI, synthetic medical images pose growing risks, including diagnostic deception and insurance fraud.
By Ching-Hao Chiu, Hao-Wei Chung, Gelei Xu, Xueyang Li, Pin-Yu Chen, John Kheir, Meysam Ghaffari, Carlos Morato, Ahmed Abbasi, Yiyu Shi
With the rapid adoption of generative AI, synthetic medical images pose growing risks, including diagnostic deception and insurance fraud. Although prior work has explored vision-language model (VLM)-based synthetic image detection, these evaluations typically consider images in isolation.
Vision-Language Large Models (VLLMs) trained on massive crawled corpora raise pressing copyright and data-provenance concerns. These concerns are particularly acute in healthcare, where patient medical images paired with clinical reports demand rigorous privacy safeguards.
DeepSSIM++ is a self‑supervised similarity metric designed to audit memorization in medical generative models at scale. It aggregates multi‑scale features and uses anatomy‑preserving augmentations to create an embedding space where cosine similarity approximates SSIM, removing the need for exact pixel‑level registration. Compared to existing baselines, DeepSSIM++ improves Macro F1 by 33–46 percentage points and speeds up large‑scale similarity computation by several orders of magnitude.
By Antonio Scardace, Francesco Guarnera, Sebastiano Battiato, Daniele Rav\`i
The paper proposes a Federated Learning framework that integrates an optimized YOLOv8 network for detecting kidney stones in CT images while preserving patient privacy. By enabling multiple medical institutions to collaboratively train a shared model without exchanging patient data, the approach complies with GDPR and HIPAA regulations. Experiments on a distributed CT dataset show a 0.733 mAP@50 and demonstrate fast, real‑time inference suitable for clinical deployment.
By Najiyya Younas, Omar Abdulkader, Yaser Ali Shah, Muhammad Jawad Ikram, Jebran Khan, Amaad Khalil
arXiv:2606. 18063v1 Announce Type: cross Abstract: Medical image classification faces a fundamental dilemma: while deep learning models achieve remarkable performance at scale, real-world clinical scenarios often suffer from severe data scarcity due to annotation costs, privacy constraints, and disease rarity.
By Ruman Wang, Hangting Ye
arXiv:2504. 14798v2 Announce Type: replace Abstract: Machine Unlearning (MUL) has emerged as a key mechanism for privacy protection and content regulation, yet current techniques often fail to guarantee the complete removal of sensitive information.
By Hao Xuan, Xingyu Li
arXiv:2606. 07640v1 Announce Type: cross Abstract: This study investigates the trade-offs between fidelity, privacy, and utility in synthetic data generation under conditions of data scarcity and privacy sensitivity.
By Borja Arroyo Galende, Alejandro Almod\'ovar, Patricia A. Apell\'aniz, Juan Parras, Silvia Uribe, Santiago Zazo
arXiv:2607. 10580v1 Announce Type: cross Abstract: AI models are increasingly trained on personal images scraped from social media and public platforms, often without consent, leading to serious privacy violations, such as unauthorized facial recognition and targeted advertising.
By Syed Irfan Ali Meerza, Oktay Ozturk, Amir Sadovnik, Jian Liu
The unprecedented growth of computer vision applications, such as surveillance systems and social media, raises security and visual privacy concerns, especially when data is stored on cloud servers. Image obfuscation offers a way to preserve visual privacy while maintaining an adequate level of usability; thus, it has been a topic of great interest in recent years.